INDEX

Explanations

mentions or references to users, usually denoted with the term 'user' followed by a number

oai_token-act-pair · gpt-3.5-turbo

mentions of "user" and related concepts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.2.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Scand

-0.79

 Baptist

-0.76

hovah

-0.75

 Hurricanes

-0.72

tackle

-0.70

 Lutheran

-0.66

erella

-0.66

erald

-0.64

 Monstrous

-0.63

 Sacrament

-0.62

POSITIVE LOGITS

 interface

0.99

 interfaces

0.94

interface

0.87

 interaction

0.84

UID

0.75

base

0.74

 upgr

0.73

atical

0.73

Interface

0.73

 user

0.72

Activations Density 0.023%

mentions or references to users, usually denoted with the term 'user' followed by a number

mentions of "user" and related concepts

No Comments

No Known Activations